Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    legal documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _gap
    -0.07
    Msp
    -0.06
    UDGE
    -0.06
     mar
    -0.06
     Erectile
    -0.06
    .Mail
    -0.06
    _edge
    -0.06
     Rahul
    -0.06
     psychologists
    -0.06
     MED
    -0.06
    POSITIVE LOGITS
    าบ
    0.07
    irie
    0.07
    ению
    0.07
    时代
    0.07
    甚至
    0.06
     failed
    0.06
     Terra
    0.06
    ного
    0.06
    SIZE
    0.06
    ，因为
    0.06
    Act Density 0.000%

    No Known Activations